Visual speech recognition remains an open research problem where different challenges must be considered by dispensing with the auditory sense, such as visual ambiguities, the inter-personal variability among speakers, and the complex modeling of silence. Nonetheless, recent remarkable results have been achieved in the field thanks to the availability of large-scale databases and the use of powerful attention mechanisms. Besides, multiple languages apart from English are nowadays a focus of interest. This paper presents noticeable advances in automatic continuous lipreading for Spanish. First, an end-to-end system based on the hybrid CTC/Attention architecture is presented. Experiments are conducted on two corpora of disparate nature, reaching state-of-the-art results that significantly improve the best performance obtained to date for both databases. In addition, a thorough ablation study is carried out, where it is studied how the different components that form the architecture influence the quality of speech recognition. Then, a rigorous error analysis is carried out to investigate the different factors that could affect the learning of the automatic system. Finally, a new Spanish lipreading benchmark is consolidated. Code and trained models are available at https://github.com/david-gimeno/evaluating-end2end-spanish-lipreading.
Audio-visual representation learning is crucial for advancing multimodal speech processing tasks, such as lipreading and audio-visual speech recognition. Recently, speech foundation models (SFMs) have shown remarkable generalization capabilities across various speech-related tasks. Building on this progress, we propose an audio-visual representation learning model that leverages cross-modal knowledge distillation from SFMs. In our method, SFMs serve as teachers, from which multi-layer hidden representations are extracted using clean audio inputs. We also introduce a multi-teacher ensemble method to distill the student, which receives audio-visual data as inputs. A novel representational knowledge distillation loss is employed to train the student during pretraining, which is also applied during finetuning to further enhance the performance on downstream tasks. Our experiments utilized both a self-supervised SFM, WavLM, and a supervised SFM, iFLYTEK-speech. The results demonstrated that our proposed method achieved superior or at least comparable performance to previous state-of-the-art baselines across automatic speech recognition, visual speech recognition, and audio-visual speech recognition tasks. Additionally, comprehensive ablation studies and the visualization of learned representations were conducted to evaluate the effectiveness of our proposed method.
Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to yield separate models, leading to disjoint inference pipelines with increased memory requirements and redundancies. This paper proposes unified training strategies for these systems. We demonstrate that training a single model for all three tasks enhances VSR and AVSR performance, overcoming typical optimisation challenges when training from scratch. Moreover, we introduce a greedy pseudo-labelling approach to more effectively leverage unlabelled samples, addressing shortcomings in related self-supervised methods. Finally, we develop a self-supervised pre-training method within our framework, proving its effectiveness alongside our semi-supervised approach. Despite using a single model for all tasks, our unified approach achieves state-of-the-art performance compared to recent methods on LRS3 and LRS2 for ASR, VSR, and AVSR, as well as on the newly released WildVSR dataset. Code and models are available at https://github.com/ahaliassos/usr.
Visual Speech Recognition (VSR) stands at the intersection of computer vision and speech recognition, aiming to interpret spoken content from visual cues. A prominent challenge in VSR is the presence of homophenes-visually similar lip gestures that represent different phonemes. Prior approaches have sought to distinguish fine-grained visemes by aligning visual and auditory semantics, but often fell short of full synchronization. To address this, we present SyncVSR, an end-to-end learning framework that leverages quantized audio for frame-level crossmodal supervision. By integrating a projection layer that synchronizes visual representation with acoustic data, our encoder learns to generate discrete audio tokens from a video sequence in a non-autoregressive manner. SyncVSR shows versatility across tasks, languages, and modalities at the cost of a forward pass. Our empirical evaluations show that it not only achieves state-of-the-art results but also reduces data usage by up to ninefold.
In visual speech processing, context modeling capability is one of the most important requirements due to the ambiguous nature of lip movements. For example, homophenes, words that share identical lip movements but produce different sounds, can be distinguished by considering the context. In this paper, we propose a novel framework, namely Visual Speech Processing incorporated with LLMs (VSP-LLM), to maximize the context modeling ability by bringing the overwhelming power of LLMs. Specifically, VSP-LLM is designed to perform multi-tasks of visual speech recognition and translation, where the given instructions control the type of task. The input video is mapped to the input latent space of an LLM by employing a self-supervised visual speech model. Focused on the fact that there is redundant information in input frames, we propose a novel deduplication method that reduces the embedded visual features by employing visual speech units. Through the proposed deduplication and Low Rank Adaptation (LoRA), VSP-LLM can be trained in a computationally efficient manner. In the translation dataset, the MuAViC benchmark, we demonstrate that VSP-LLM trained on just 30 hours of labeled data can more effectively translate lip movements compared to the recent model trained with 433 hours of data.
Audio-visual speech recognition has received a lot of attention due to its robustness against acoustic noise. Recently, the performance of automatic, visual, and audio-visual speech recognition (ASR, VSR, and AV-ASR, respectively) has been substantially improved, mainly due to the use of larger models and training sets. However, accurate labelling of datasets is time-consuming and expensive. Hence, in this work, we investigate the use of automatically-generated transcriptions of unlabelled datasets to increase the training set size. For this purpose, we use publicly-available pre-trained ASR models to automatically transcribe unlabelled datasets such as AVSpeech and VoxCeleb2. Then, we train ASR, VSR and AV-ASR models on the augmented training set, which consists of the LRS2 and LRS3 datasets as well as the additional automatically-transcribed data. We demonstrate that increasing the size of the training set, a recent trend in the literature, leads to reduced WER despite using noisy transcriptions. The proposed model achieves new state-of-the-art performance on AV-ASR on LRS2 and LRS3. In particular, it achieves a WER of 0.9% on LRS3, a relative improvement of 30% over the current state-of-the-art approach, and outperforms methods that have been trained on non-publicly available datasets with 26 times more training data.
Silent speech interface is a promising technology that enables private communications in natural language. However, previous approaches only support a small and inflexible vocabulary, which leads to limited expressiveness. We leverage contrastive learning to learn efficient lipreading representations, enabling few-shot command customization with minimal user effort. Our model exhibits high robustness to different lighting, posture, and gesture conditions on an in-the-wild dataset. For 25-command classification, an F1-score of 0.8947 is achievable only using one shot, and its performance can be further boosted by adaptively learning from more data. This generalizability allowed us to develop a mobile silent speech interface empowered with on-device fine-tuning and visual keyword spotting. A user study demonstrated that with LipLearner, users could define their own commands with high reliability guaranteed by an online incremental learning scheme. Subjective feedback indicated that our system provides essential functionalities for customizable silent speech interactions with high usability and learnability.
We present RAVEn, a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our pre-training objective involves encoding masked inputs, and then predicting contextualised targets generated by slowly-evolving momentum encoders. Driven by the inherent differences between video and audio, our design is asymmetric w.r.t. the two modalities' pretext tasks: Whereas the auditory stream predicts both the visual and auditory targets, the visual one predicts only the auditory targets. We observe strong results in low- and high-resource labelled data settings when fine-tuning the visual and auditory encoders resulting from a single pre-training stage, in which the encoders are jointly trained. Notably, RAVEn surpasses all self-supervised methods on visual speech recognition (VSR) on LRS3, and combining RAVEn with self-training using only 30 hours of labelled data even outperforms a recent semi-supervised method trained on 90,000 hours of non-public data. At the same time, we achieve state-of-the-art results in the LRS3 low-resource setting for auditory speech recognition (as well as for VSR). Our findings point to the viability of learning powerful speech representations entirely from raw video and audio, i.e., without relying on handcrafted features. Code and models are available at https://github.com/ahaliassos/raven.
Several training strategies and temporal models have been recently proposed for isolated word lip-reading in a series of independent works. However, the potential of combining the best strategies and investigating the impact of each of them has not been explored. In this paper, we systematically investigate the performance of state-of-the-art data augmentation approaches, temporal models and other training strategies, like self-distillation and using word boundary indicators. Our results show that Time Masking (TM) is the most important augmentation followed by mixup and Densely-Connected Temporal Convolutional Networks (DC-TCN) are the best temporal model for lip-reading of isolated words. Using self-distillation and word boundary indicators is also beneficial but to a lesser extent. A combination of all the above methods results in a classification accuracy of 93.4%, which is an absolute improvement of 4.6% over the current state-of-the-art performance on the LRW dataset. The performance can be further improved to 94.1% by pre-training on additional datasets. An error analysis of the various training strategies reveals that the performance improves by increasing the classification accuracy of hard-to-recognise words.
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when given limited training data. To this end, an overarching full Bayesian learning framework encompassing three methods is proposed in this paper to account for the underlying uncertainty in LSTM-RNN and Transformer LMs. The uncertainty over their model parameters, choice of neural activations and hidden output representations are modeled using Bayesian, Gaussian Process and variational LSTM-RNN or Transformer LMs respectively. Efficient inference approaches were used to automatically select the optimal network internal components to be Bayesian learned using neural architecture search. A minimal number of Monte Carlo parameter samples as low as one was also used. These allow the computational costs incurred in Bayesian NNLM training and evaluation to be minimized. Experiments are conducted on two tasks: AMI meeting transcription and Oxford-BBC LipReading Sentences 2 (LRS2) overlapped speech recognition using state-of-the-art LF-MMI trained factored TDNN systems featuring data augmentation, speaker adaptation and audio-visual multi-channel beamforming for overlapped speech. Consistent performance improvements over the baseline LSTM-RNN and Transformer LMs with point estimated model parameters and drop-out regularization were obtained across both tasks in terms of perplexity and word error rate (WER). In particular, on the LRS2 data, statistically significant WER reductions up to 1.3% and 1.2% absolute (12.1% and 11.3% relative) were obtained over the baseline LSTM-RNN and Transformer LMs respectively after model combination between Bayesian NNLMs and their respective baselines.
Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the multimodal AVSR. In particular, audio and visual front-ends are trained on large-scale unimodal datasets, then we integrate components of both front-ends into a larger multimodal framework which learns to recognize parallel audio-visual data into characters through a combination of CTC and seq2seq decoding. We show that both components inherited from unimodal self-supervised learning cooperate well, resulting in that the multimodal framework yields competitive results through fine-tuning. Our model is experimentally validated on both word-level and sentence-level tasks. Especially, even without an external language model, our proposed model raises the state-of-the-art performances on the widely accepted Lip Reading Sentences 2 (LRS2) dataset by a large margin, with a relative improvement of 30%.
Visual speech recognition (VSR) aims to recognize the content of speech based on lip movements, without relying on the audio stream. Advances in deep learning and the availability of large audio-visual datasets have led to the development of much more accurate and robust VSR models than ever before. However, these advances are usually due to the larger training sets rather than the model design. Here we demonstrate that designing better models is equally as important as using larger training sets. We propose the addition of prediction-based auxiliary tasks to a VSR model, and highlight the importance of hyperparameter optimization and appropriate data augmentations. We show that such a model works for different languages and outperforms all previous methods trained on publicly available datasets by a large margin. It even outperforms models that were trained on non-publicly available datasets containing up to to 21 times more data. We show, furthermore, that using additional training data, even in other languages or with automatically generated transcriptions, results in further improvement.
Video recordings of speech contain correlated audio and visual information, providing a strong signal for speech representation learning from the speaker's lip movements and the produced sound. We introduce Audio-Visual Hidden Unit BERT (AV-HuBERT), a self-supervised representation learning framework for audio-visual speech, which masks multi-stream video input and predicts automatically discovered and iteratively refined multimodal hidden units. AV-HuBERT learns powerful audio-visual speech representation benefiting both lip-reading and automatic speech recognition. On the largest public lip-reading benchmark LRS3 (433 hours), AV-HuBERT achieves 32.5% WER with only 30 hours of labeled data, outperforming the former state-of-the-art approach (33.6%) trained with a thousand times more transcribed video data (31K hours). The lip-reading WER is further reduced to 26.9% when using all 433 hours of labeled data from LRS3 and combined with self-training. Using our audio-visual representation on the same benchmark for audio-only speech recognition leads to a 40% relative WER reduction over the state-of-the-art performance (1.3% vs 2.3%). Our code and models are available at https://github.com/facebookresearch/av_hubert
Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker. However, previous AVSR work focused solely on the supervised learning setup; hence the progress was hindered by the amount of labeled data available. In this work, we present a self-supervised AVSR framework built upon Audio-Visual HuBERT (AV-HuBERT), a state-of-the-art audio-visual speech representation learning model. On the largest available AVSR benchmark dataset LRS3, our approach outperforms prior state-of-the-art by ~50% (28.0% vs. 14.1%) using less than 10% of labeled data (433hr vs. 30hr) in the presence of babble noise, while reducing the WER of an audio-based model by over 75% (25.8% vs. 5.8%) on average.
Although current deep learning-based face forgery detectors achieve impressive performance in constrained scenarios, they are vulnerable to samples created by unseen manipulation methods. Some recent works show improvements in generalisation but rely on cues that are easily corrupted by common post-processing operations such as compression. In this paper, we propose LipForensics, a detection approach capable of both generalising to novel manipulations and withstanding various distortions. LipForensics targets high-level semantic irregularities in mouth movements, which are common in many generated videos. It consists in first pretraining a spatio-temporal network to perform visual speech recognition (lipreading), thus learning rich internal representations related to natural mouth motion. A temporal network is subsequently finetuned on fixed mouth embeddings of real and forged data in order to detect fake videos based on mouth movements without overfitting to low-level, manipulation-specific artefacts. Extensive experiments show that this simple approach significantly surpasses the state-of-the-art in terms of generalisation to unseen manipulations and robustness to perturbations, as well as shed light on the factors responsible for its performance. Code is available on GitHub.
Lip reading, also known as visual speech recognition, aims to recognize the speech content from videos by analyzing the lip dynamics. There have been several appealing progress in recent years, benefiting much from the rapidly developed deep learning techniques and the recent large-scale lip-reading datasets. Most existing methods obtained high performance by constructing a complex neural network, together with several customized training strategies which were always given in a very brief description or even shown only in the source code. We find that making proper use of these strategies could always bring exciting improvements without changing much of the model. Considering the non-negligible effects of these strategies and the existing tough status to train an effective lip reading model, we perform a comprehensive quantitative study and comparative analysis, for the first time, to show the effects of several different choices for lip reading. By only introducing some easy-to-get refinements to the baseline pipeline, we obtain an obvious improvement of the performance from 83.7% to 88.4% and from 38.2% to 55.7% on two largest public available lip reading datasets, LRW and LRW-1000, respectively. They are comparable and even surpass the existing state-of-the-art results.
Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. However, there is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. In this work, we propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation. Secondly, we propose a series of architectural changes, including a novel Depthwise Separable Temporal Convolutional Network (DS-TCN) head, that slashes the computational cost to a fraction of the (already quite efficient) original model. Thirdly, we show that knowledge distillation is a very effective tool for recovering performance of the lightweight models. This results in a range of models with different accuracy-efficiency trade-offs. However, our most promising lightweight models are on par with the current state-of-the-art while showing a reduction of 8.2x and 3.9x in terms of computational cost and number of parameters, respectively, which we hope will enable the deployment of lipreading models in practical applications.
This paper presents a novel deep learning architecture for word-level lipreading. Previous works suggest a potential for incorporating a pretrained deep 3D Convolutional Neural Networks as a front-end feature extractor. We introduce a SpotFast networks, a variant of the state-of-the-art SlowFast networks for action recognition, which utilizes a temporal window as a spot pathway and all frames as a fast pathway. We further incorporate memory augmented lateral transformers to learn sequential features for classification. We evaluate the proposed model on the LRW dataset. The experiments show that our proposed model outperforms various state-of-the-art models and incorporating the memory augmented lateral transformers makes a 3.7% improvement to the SpotFast networks.
Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded to the multi-modality speech recognition (MSR). In this paper, we propose a two-stage speech recognition model. In the first stage, the target voice is separated from background noises with help from the corresponding visual information of lip movements, making the model 'listen' clearly. At the second stage, the audio modality combines visual modality again to better understand the speech by a MSR sub-network, further improving the recognition rate. There are some other key contributions: we introduce a pseudo-3D residual convolution (P3D)-based visual front-end to extract more discriminative features; we upgrade the temporal convolution block from 1D ResNet with the temporal convolutional network (TCN), which is more suitable for the temporal tasks; the MSR sub-network is built on the top of Element-wise-Attention Gated Recurrent Unit (EleAtt-GRU), which is more effective than Transformer in long sequences. We conducted extensive experiments on the LRS3-TED and the LRW datasets. Our two-stage model (audio enhanced multi-modality speech recognition, AE-MSR) consistently achieves the state-of-the-art performance by a significant margin, which demonstrates the necessity and effectiveness of AE-MSR.
Lip reading has received an increasing research interest in recent years due to the rapid development of deep learning and its widespread potential applications. One key point to obtain good performance for the lip reading task depends heavily on how effective the representation can be to capture the lip movement information and meanwhile to resist the noises resulted from the change of pose, lighting conditions, speaker's appearance and so on. Towards this target, we propose to introduce the mutual information constraints on both the local feature's level and the global sequence's level to enhance the relations of the features with the speech content. On the one hand, we constraint the features generated at each time step to enable them carry a strong relation with the speech content by imposing the local mutual information maximization constraint (LMIM), leading to improvements over the model's ability to discover fine-grained lip movements and the fine-grained differences among words with similar pronunciation, such as ``spend'' and ``spending''. On the other hand, we introduce the mutual information maximization constraint on the global sequence's level (GMIM), to make the model be able to pay more attention to discriminate key frames related with the speech content, and less to various noises appeared in the speaking process. By combining these two advantages together, the proposed method is expected to be both discriminative and robust for effective lip reading. To verify this method, we evaluate on two large-scale benchmark. We perform a detailed analysis and comparison on several aspects, including the comparison of the LMIM and GMIM with the baseline, the visualization of the learned representation and so on. The results not only prove the effectiveness of the proposed method but also report new state-of-the-art performance on both the two benchmarks.